Triple
T19436437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epic Beacon |
E486234
|
entity |
| Predicate | integratesWith |
P1075
|
FINISHED |
| Object | Epic MyChart |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Epic MyChart | Statement: [Epic Beacon, integratesWith, Epic MyChart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Epic MyChart Context triple: [Epic Beacon, integratesWith, Epic MyChart]
-
A.
MyChart
chosen
MyChart is a widely used patient portal application by Epic Systems that lets individuals securely access and manage their personal health information online.
-
B.
EpicCare Ambulatory
EpicCare Ambulatory is Epic Systems’ electronic health record module designed to support clinical workflows and documentation in outpatient and ambulatory care settings.
-
C.
Health Connect
Health Connect is a unified health and fitness data platform on Android that lets apps securely share and manage users’ wellness information in one place.
-
D.
Allscripts
Allscripts is a healthcare information technology company known for providing electronic health record (EHR), practice management, and related software solutions to hospitals and physician practices.
-
E.
EMR Notebooks
EMR Notebooks are managed Jupyter notebook environments in Amazon EMR that let users interactively develop, visualize, and run big data applications on EMR clusters.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8e8d7ad488190a3373045029b0f3b |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633618c2881908f3d2a9cabb02289 |
completed | April 20, 2026, 2:08 p.m. |
Created at: April 10, 2026, 1:38 p.m.